Title:
VOICE AUTHENTICATION SYSTEM INTO WHICH WATERMARK IS INSERTED, AND METHOD THEREFOR
Document Type and Number:
WIPO Patent Application WO/2021/182683
Kind Code:
A1
Abstract:
The present invention provides a voice authentication system. A voice authentication system according to one embodiment of the present invention comprises: a voice collecting unit for collecting voice information obtained by digitizing a speaker's voice; a learning model server for generating a voice image on the basis of the collected speaker's voice information, causing a deep neural network (DNN) model to learn the voice image, and extracting a feature vector for the voice image; a watermark server for generating a watermark on the basis of the feature vector and inserting the watermark and individual information into the voice image or voice conversion data; and an authentication server for generating a private key on the basis of the feature vector and determining whether to extract the watermark and the individual information according to an authentication result.
Inventors:
JUN HA RIN (KR)
Application Number:
PCT/KR2020/009436
Publication Date:
September 16, 2021
Filing Date:
July 17, 2020
Export Citation:
Assignee:
PUZZLE AI CO LTD (KR)
International Classes:
G10L17/04; G06F3/08; G06F21/32; G06F21/62; G10L17/18; G10L19/018; G10L25/15; G10L25/18
Foreign References:
| KR20200020213A | 2020-02-26 | |||
| KR20190141350A | 2019-12-24 | |||
| US20140108020A1 | 2014-04-17 | |||
| KR20150105806A | 2015-09-18 | |||
| US6615171B1 | 2003-09-02 | |||
| KR20190135657A | 2019-12-09 |
Attorney, Agent or Firm:
SUAN INTELLECTUAL PROPERTY (KR)
Download PDF: